Senior/Staff Software Engineer - Machine Learning & System Optimization

📋 Description

• Allocate and distribute system resources to models on the robot.
• Spearhead compute sharing and scheduling improvements across models.
• Optimize large-scale models with quantization, pruning, mixed precision.
• Architect model conversion/compilation pipelines using TensorRT.
• Write production-grade C++ and CUDA for real-time vehicle inference.

🎯 Requirements

• Deep experience in CPU/GPU system optimization for low latency.
• Real-time systems expertise with latency and memory constraints.
• Model quantization PTQ/QAT and mixed-precision (INT8, FP8, BF16/FP16).
• Low-level programming for AI accelerators; develop TensorRT ops and CUDA kernels.
• Production C++ (14/17/20) and Python for edge, concurrent code.
• Prior experience in high-performance robotics (AV/drones/robots).

🎁 Benefits

• Paid time off
• Unpaid time off
• Zoox Stock Appreciation Rights
• Amazon RSUs
• Health insurance
• Sign-on bonus may be offered